Model Catalog

Browse our selection of hand-picked, ready-to-deploy models!

All Hub Models

Text Generation

Author avatar

Meta-Llama-3-70B-Instruct

TGI
Text Generation
meta-llama

A 70-billion parameter model from Meta, optimized for dialogue. Generates helpful, safe responses and outperforms other open-source chat LLMs.

$
16 / h
Go
Author avatar

gemma-7b-it

TGI
Text Generation
google

A instruction model fine-tuned from Gemma 7B Googles, first open LLM.

$
0.8 / h
Go
Author avatar

OpenHermes-2.5-Mistral-7B-GPTQ

TGI
Text Generation
TheBloke

A powerful chat model fine-tuned from Mistral 7B on a large corpus of synthetic data. Capable of function-calling and has strong coding capabilities.

$
0.8 / h
Go
Author avatar

NeuralHermes-2.5-Mistral-7B-GPTQ

TGI
Text Generation
TheBloke

A fine-tuned version of OpenHermes 2.5 that was aligned with Direct Preference Optimization and AI preference examples from the SlimOrca dataset.

$
0.8 / h
Go
Author avatar

Starling-LM-7B-alpha

TGI
Text Generation
berkeley-nest

Open chat language model by UC Berkeley. Outperformed all 7B models at the time of its release. For non-commercial use only.

$
0.8 / h
Go
Author avatar

openchat-3.5-0106

TGI
Text Generation
openchat

Open source large language model that targets high performance and commercial viability. Fine-tuned using C-RLFT, for results on par with ChatGPT.

$
0.8 / h
Go
Author avatar

Mistral-7B-Instruct-v0.1

TGI
Text Generation
mistralai

A 7-billion parameter instruct model from Mistral AI, fine-tuned using a variety of publicly available conversation datasets.

$
0.8 / h
Go
Author avatar

zephyr-7b-beta

TGI
Text Generation
huggingFaceH4

A chat model fine-tuned from Mistral 7B with synthetic data and Direct Preference Optimization.

$
0.8 / h
Go
Author avatar

neural-chat-7b-v3-1

TGI
Text Generation
Intel

A chat model from Intel fine-tuned from Mistral 7B on the SlimOrca dataset with Direct Preference Optimization.

$
0.8 / h
Go
Author avatar

Llama-2-13B-chat-GPTQ

TGI
Text Generation
TheBloke

A 13-billion parameter model from Meta, optimized for dialogue. Generates helpful, safe responses and outperforms other open-source chat models.

$
0.8 / h
Go
Author avatar

Llama-2-70B-chat-GPTQ

TGI
Text Generation
TheBloke

A 70-billion parameter model from Meta, optimized for dialogue. Generates helpful, safe responses and outperforms other open-source chat LLMs.

$
8 / h
Go
Author avatar

Falcon-180B-Chat-GPTQ

TGI
Text Generation
TheBloke

A 180-billion parameter conversational AI model optimized for fast inference through an efficient architecture. Freely available under TII LICENSE.

$
8 / h
Go
Author avatar

Mixtral-8x7B-Instruct-v0.1

TGI
Text Generation
mistralai

Mixtral 8x7B is a sparse mixture-of-experts decoder-only model fine-tuned on instruction following a permissive license.

$
8 / h
Go

Text-to-Image

Text-to-Image
runwayml

Latent text-to-image diffusion model capable of generating photo-realistic images given any text input.

$
0.5 / h
Go
Text-to-Image
Linaqruf

Advanced latent diffusion model designed to create high-resolution, detailed anime images. Fine-tuned from Stable Diffusion XL 1.0.

$
0.8 / h
Go
Text-to-Image
stabilityai

Latent Diffusion model from Stability AI for high-quality, diverse image generation based on short text prompts provided by the user.

$
0.8 / h
Go
Text-to-Image
prompthero

Open source Stable Diffusion fine-tuned model on Midjourney images.

$
0.8 / h
Go
Text-to-Image
stablediffusionapi

Fine-tuned model based on Stable Diffusion designed to generate anime characters.

$
0.8 / h
Go

Sentence Embeddings

Author avatar

all-MiniLM-L6-v2

TEI
Sentence Embeddings
sentence-transformers

This model maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.

$
0.032 / h
Go
Sentence Embeddings
sentence-transformers

This model maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

$
0.064 / h
Go
Author avatar

bge-base-en-v1.5

TEI
Sentence Embeddings
BAAI

BGE models from BAAI are optimized for retrieval and search. The 'base' variant is ranked 2nd in the MTEB English leaderboard

$
0.128 / h
Go
Author avatar

multilingual-e5-large

TEI
Sentence Embeddings
intfloat

This model is initialized from xlm-roberta-large and continually trained on a mixture of multilingual datasets. It supports 100 languages.

$
0.5 / h
Go
Author avatar

paraphrase-multilingual-MiniLM-L12-v2

TEI
Sentence Embeddings
sentence-transformers

This model maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.

$
0.8 / h
Go
Author avatar

ember-v1

TEI
Sentence Embeddings
llmrails

Model trained on an extensive corpus of text pairs belonging to domains such as finance, science, medicine, law, and various others.

$
0.8 / h
Go
Author avatar

bge-large-en-v1.5

TEI
Sentence Embeddings
BAAI

BGE models from BAAI are optimized for retrieval and search. The 'large' variant is ranked 1st in the MTEB English leaderboard

$
0.8 / h
Go

Sentence Ranking

Sentence Ranking
cross-encoder

SBERT model which can be used for Information Retrieval by scores query+paragraph. Can be combined with embedding models.

$
0.032 / h
Go
Sentence Ranking
BAAI

SBERT model which can be used for Information Retrieval by scores query+paragraph. Can be combined with embedding models.

$
0.8 / h
Go

Zero-Shot Classification

Zero-Shot Classification
MoritzLaurer

An English-only model specialized in zeroshot text classification trained on 33 diverse datasets. 0.43B parameters small and more efficient than generative LLMs.

$
0.5 / h
Go
Zero-Shot Classification
MoritzLaurer

A multilingual model specialized in zeroshot text classification trained on 33 diverse datasets. 0.57B parameters small and more efficient than generative LLMs.

$
0.5 / h
Go
Zero-Shot Classification
facebook

Version of the bart-large model trained on the MultiNLI (MNLI) dataset.

$
0.5 / h
Go

Automatic Speech Recognition

Automatic Speech Recognition
distil-whisper

Distilled version of the Whisper model that is 6 times faster, 49% smaller, and performs within 1% WER on out-of-distribution evaluation sets.

$
0.8 / h
Go
Automatic Speech Recognition
openai

New version of the whisper-large model showing improved performance over a wide variety of languages, with 10% to 20% reduction of errors compared to Whisper large-v2.

$
0.8 / h
Go